{"record":{"id":"9f55a3680b4bae43","repo":"BerriAI/litellm","slug":"nothing-to-run","errorCode":null,"errorMessage":"Nothing to run.","messagePattern":"Nothing to run\\.","errorType":"exception","errorClass":"AgentRunError","httpStatus":null,"severity":"error","filePath":"litellm/proxy/client/cli/commands/agents.py","lineNumber":277,"sourceCode":"    api_key: str,\n    command: Sequence[str],\n    *,\n    skip_verify: bool = False,\n    base_env: Mapping[str, str] | None = None,\n    which: Callable[[str], str | None] = shutil.which,\n    verify: Callable[[str, str], None] = verify_proxy_key,\n    launcher: Callable[[str, Sequence[str], Mapping[str, str]], None] = _hand_off,\n    reattach_terminal: Callable[[], None] | None = None,\n) -> None:\n    \"\"\"Validate, wire the environment, and hand off to the agent.\n\n    On success this never returns: POSIX replaces the current process, Windows\n    waits on the agent and exits with its status. Raises AgentRunError for\n    missing binaries, an unreachable proxy, or a rejected key.\n    reattach_terminal, when given, runs just before handoff to restore stdin.\n    \"\"\"\n    if not command:\n        raise AgentRunError(\"Nothing to run.\")\n\n    _, profiles = agent_profile(command[0])\n    binary: Final = which(command[0])\n    if binary is None:\n        docs: Final = _INSTALL_DOCS.get(os.path.basename(command[0]))\n        hint: Final = f\" Install it first: {docs}\" if docs else \"\"\n        raise AgentRunError(f\"Could not find `{command[0]}` on your PATH.{hint}\")\n\n    if not skip_verify:\n        verify(base_url, api_key)\n\n    env: Final = build_agent_env(\n        base_env if base_env is not None else os.environ,\n        base_url,\n        api_key,\n        profiles,\n    )\n    extra_args: Final = agent_launch_args(command[0], base_url)","sourceCodeStart":259,"sourceCodeEnd":295,"githubUrl":"https://github.com/BerriAI/litellm/blob/77b7c6c40c0c5aa5fbcb1d6a1825ac39ca8829b8/litellm/proxy/client/cli/commands/agents.py#L259-L295","documentation":"Raised by the CLI agent-launch pre-flight when the resolved command sequence is empty — the agent config supplied no executable to hand off to. The launcher is about to exec a process; with no command there is nothing to run, so the handoff aborts immediately with AgentRunError before any proxy communication or environment wiring happens.","triggerScenarios":"Thrown at litellm/proxy/client/cli/commands/agents.py:277 when the library encounters an invalid state.","commonSituations":"The agents command was invoked without anything to execute.","solutions":["Provide a command or prompt for the agent to run."],"exampleFix":"lite agents run -- <command>","handlingStrategy":"validation","validationCode":null,"typeGuard":null,"tryCatchPattern":null,"preventionTips":[],"tags":[],"backgroundTag":null,"analyzedSha":"77b7c6c40c0c5aa5fbcb1d6a1825ac39ca8829b8","analyzedAt":"2026-08-18T11:44:31.656Z","contentChangedAt":null,"schemaVersion":2},"datasetVersion":"2026-09-14T05:17:10.506Z"}